© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9488
    Prev
    Next
    INDEX
    Explanations

    scientific data and processes

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific or technical terms related to data, research, or computational analysis.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     problemu
    -1.80
     asegura
    -1.77
    ཫ
    -1.70
    vlád
    -1.69
     jednej
    -1.66
     musisz
    -1.66
     wiesz
    -1.62
     Garantía
    -1.59
     Reised
    -1.58
     oblasti
    -1.55
    POSITIVE LOGITS
     geforce
    1.53
    maksi
    1.50
    雰
    1.48
     citroen
    1.48
    prende
    1.46
     deres
    1.41
    šní
    1.40
     髪
    1.40
     gånger
    1.38
     stund
    1.36
    Activations Density 0.814%

    No Known Activations